arXiv cs.AI· Minxing Chu, Anhang Li, Martins Atilla, Ruichen Qi, Mehdi Saligane·· 14 小时前AI 评分34
模拟版图生成器背后的代码：用 AI 智能体为 gLayout 编写生成器
The Code Behind the Layout: AI Agents for Analog Layout Generators
AI 导读
在 SKY130 上对 gLayout 的受控实验显示，让 LLM 直接绘制模拟版图的主要障碍是时间与 token 成本，而基于生成器框架的最大优势是可复用性。模型最有效的用法是针对设计意图所属版图族的生成器源码进行开发，并在最可能失败的族成员上验证每次编辑，使一次验证过的修改改进该生成器产出的所有版图。这些族测试结果还可作为本地模型的监督信号，以极低的推理成本学会跨族通用的编辑。
正文 · 原文
Abstract:Analog layout remains largely manual and hard to automate. Generator frameworks such as gLayout express layouts as programs, producing layouts from parameterized, design-rule-aware generators; however, writing such generators still takes expert effort. Large language models (LLMs) could now write generator code, and frontier models can even draw layout geometry from design intent. This raises a practical question: if a model can draw the layout itself, what does a generator framework still contribute, and is applying these models to a generator framework better than having them draw a layout from scratch? Through controlled experiments on gLayout in SKY130, we find that the main obstacle to drawing a layout directly is its time and token cost, and that the main advantage of a model building on a generator framework is reusability. Its verified primitives keep each model edit small enough to check, and its parameters allow a single edit to be evaluated across an entire family of layouts. Accordingly, a model is most effective when it develops the layout from the generator source of the family that the design intent belongs to, and tests each edit on the family members most likely to fail, so that one verified change improves every layout the generator produces. The results of these family tests can then serve as supervision for a local model, which learns edits that hold across the family at a fraction of the inference cost.
| Subjects: | Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.38426 [cs.AR] |
| (or arXiv:2610.38426v1 [cs.AR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38426 arXiv-issued DOI via DataCite |
Submission history
From: Minxing Chu [view email]
[v1]
Wed, 28 Oct 2026 08:10:12 UTC (242 KB)
来源：arXiv cs.AI · arxiv.org